🏅 To me, this feels more like the kind of neural model interpretability research we should be doing than much of the recent work on interpretability of transformer models.
The Israeli military is bombing Rafah, the most densely populated area in the world, while Americans watch the Super Bowl. This is intentional. This is genocide.
We're demanding the world watching the #superbowl turn their eyes to #Rafah. #alleyesongaza#CeasefireNOW
***Feb 5 DEADLINE*** Tenure-Track Faculty Position in ML/CV at University of Cambridge.
https://t.co/E1p7YbOg7H
I would be very excited for candidates interested in AI safety, ethics, and/or social impacts of AI to apply (TBC, I am not on the hiring committee).
If you are considering applying, you are welcome to reach out (please send me relevant info, e.g. any materials you happen to have on hand).
Note that the application materials are shorter than a typical North American one:
- Curriculum Vitae (CV)
- A full publications list
- A statement which covers professional, teaching and research experience and describe your future research plans (no more than two pages in total);
- Cover letter
New work on Geometric Clifford Algebra Networks (GCANs). We propose geometric templates for modeling dynamical systems. A 🧵on geometric / Clifford algebras, and symmetry group transformations in neural networks.
📜https://t.co/ugW5HAgFi6
(3/12) GCANs build on Clifford neural layers by @jo_brandstetter, @vdbergrianne, @rejuvyesh, @wellingmax, but with strong emphasis on geometry which we model via plane-based geometric algebra.
https://t.co/cQ6TZgG4Ec
⏰ @NeurIPSConf poster sessions start in one hour! See you all in Hall J to chat about Multi-Agent RL.
📰 “Towards a Standardised Performance Evaluation Protocol for Cooperative MARL” (#927)
📰 “Universally Expressive Communication in Multi-Agent Reinforcement Learning” (#118)
Our paper (accepted at @CoLLAs_Conf) is out!
https://t.co/7GKg90dPZ2
We show that Meta-Learning generalization to novel OOD task distributions can be inferred from the neural activation dynamics from a few unlabeled examples, and we propose Activation-Based Early-Stopping (ABE).
How Do Vision Transformers Work?
"...we propose AlterNet, a model in which Conv blocks at the end of a stage are replaced with MSA blocks. AlterNet outperforms CNNs not only in large data regimes but also in small data regimes."
https://t.co/edPXnu0cn8
CoLLAs 2022 CFP is out! Highlights: Proceedings in PMLR, revise-resubmit option, 9 pages + an optional 10th page to avoid wasting hours fitting your paper to a strict page limit, appendix in same pdf.
«Introduction to Probability for Data Science» by @stanley_h_chan, with video lectures, exercises, and Python, MATLAB, Julia, R code! 🤩🤩🤩
https://t.co/eRljUCIqtM
The only question reviewers should be asking themselves:
"Is the community better off with this paper, or without it?"
inappropriate reasons for rejection include: not beating SOTA, bad writing, minor flaws, no theory yet good results, incomplete citations (easily fixed),.....
Join @lilianweng and @_jongwook_kim tonight (Mon 6 Dec ’21) at NeurIPS' «Self-Supervised Learning: Self-Prediction and Contrastive Learning» at 20:00 EST.
@ermgrant and I will be entertaining you as session chairs.
https://t.co/JGqxoJtZ63
As long as #Africa is not vaccinated we won't rest easy. If we don't want to learn the full Greek alphabet and invent some more, we need to seriously assist the rest of the world to get access and to administer the #COVID19Vaccine.
I am looking for 1-2 PhD students to join my research group at Cambridge (CBL) fall 2022.
Our focus is on Deep Learning, AI Alignment, and existential safety.
Deadline for university funding is December 2.
I am joining @SFU_CompSci as an Assistant Professor. I am looking to recruit MSc/Ph.D. students for Fall'22. Topics of interest include sequential decision-making under uncertainty (reinforcement learning/bandit problems) and optimization for machine learning.
Check out our recent work "Instance-Conditioned GAN", a joint work with Marlene Careil, Jakob Verbeek, @adri_romsor and @michal_drozdzal.
We can generate images of unfamiliar scenes, such as camels in the snow!
Check out the details, paper and code in the blog post.
I will be teaching a course on robot learning, starting in January 2022! This course will focus on deep reinforcement learning methods and their application to robotics. You can find more info on the course here:
https://t.co/Sr1ic5KpRG